Related papers: Constrained Error Pattern Generation for GRAND
Code Large Language Models (Code LLMs) have been increasingly used by developers to boost productivity, but they often generate vulnerable code. Thus, there is an urgent need to ensure that code generated by Code LLMs is correct and secure.…
Filtering and parameter estimation under partial information for multiscale problems is studied in this paper. After proving mean square convergence of the nonlinear filter to a filter of reduced dimension, we establish that the conditional…
In NMT we search for the mode of the model distribution to form predictions. The mode and other high-probability translations found by beam search have been shown to often be inadequate in a number of ways. This prevents improving…
In this paper, we focus on the demodulation/decoding of the complex modulations/codes that approach the Shannon capacity. Theoretically, the maximum likelihood (ML) algorithm can achieve the optimal error performance whereas it has…
Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematical, and conditional constraints from natural language into the planning problem. Such constraints…
As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challenge is to aggregate a weighted combination of requirement…
We propose a method to optimize the representation and distinguishability of samples from two probability distributions, by maximizing the estimated power of a statistical test based on the maximum mean discrepancy (MMD). This optimized MMD…
Adapting Large Language Models (LLMs) for recommendation requires careful consideration of the decoding process, given the inherent differences between generating items and natural language. Existing approaches often directly apply LLMs'…
In this paper, we first introduce the concept of elementary linear subspace, which has similar properties to those of a set of coordinates. Using this new concept, we derive properties of maximum rank distance (MRD) codes that parallel…
We are motivated by problems that arise in a number of applications such as Online Marketing and Explosives detection, where the observations are usually modeled using Poisson statistics. We model each observation as a Poisson random…
In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach…
Standard decoding strategies for text generation, including top-k, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting selection to high-probability regions. Human language production operates…
Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the…
Learning a Gaussian Mixture Model (GMM) is hard when the number of parameters is too large given the amount of available data. As a remedy, we propose restricting the GMM to a Gaussian Markov Random Field Mixture Model (GMRF-MM), as well as…
Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences,…
How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? This question has been well studied in scenarios where there is no restriction on the number of LLM…
Code generation has been greatly enhanced by the profound advancements in Large Language Models (LLMs) recently. Nevertheless, such LLM-based code generation approaches still struggle to generate error-free code in a few tries when faced…
We propose Dijkstra's algorithm with bounded list size after QR decomposition for decreasing the computational complexity of near maximum-likelihood (ML) detection of signals over multiple-input-multiple-output (MIMO) channels. After that,…
Large Language Models (LLMs) excel at code generation but struggle with complex problems. Retrieval-Augmented Generation (RAG) mitigates this issue by integrating external knowledge, yet retrieval models often miss relevant context, and…
In most constraint programming systems, a limited number of search engines is offered while the programming of user-customized search algorithms requires low-level efforts, which complicates the deployment of such algorithms. To alleviate…